Efficient flight operations based on naturally present energy sources or sinks

1. An aerial vehicle comprising: an airspeed sensor; an altimeter; a position sensor; a thermometer; at least one propulsion motor; and a control system having at least one computer processor, wherein the control system is in communication with each of the airspeed sensor, the altimeter, the position sensor, the thermometer, and the at least one propulsion motor, and wherein the control system is configured to execute a method comprising: determining a first airspeed of the aerial vehicle at a first time, wherein the at least one propulsion motor is operating at a first power level at the first time; determining a first altitude above a first ground-based location of the aerial vehicle at the first time; determining a first temperature of air at the first altitude above the first ground-based location at the first time; determining that the aerial vehicle is at a second altitude at a second time; in response to determining that the aerial vehicle is at the second altitude at the second time, determining a second airspeed of the aerial vehicle at the second time, wherein the at least one propulsion motor is operating at a second power level at the second time; determining a second altitude above a second ground-based location of the aerial vehicle at the second time; determining a second temperature of air at the second altitude above the second ground-based location at the second time; calculating a first energy level of the aerial vehicle at the first time based at least in part on at least one of: a product of one-half of a mass of the aerial vehicle and a square of the first airspeed; a product of the mass of the aerial vehicle, an acceleration constant due to gravity and the first altitude; and the first power level; calculating a second energy level of the aerial vehicle at the second time based at least in part on at least one of: a product of one-half of the mass of the aerial vehicle and a square of the second airspeed; a product of the mass of the aerial vehicle, the acceleration constant due to gravity and the second altitude; and the second power level; determining a difference between the first energy level and the second energy level; attributing the difference between the first energy level and the second energy level to a difference between the first temperature and the second temperature; generating a map of at least a portion of a region including at least the second ground-based location, wherein the map comprises an indicator of naturally present energy at the second ground-based location; and storing at least the map of at least the portion of the region in at least one data store, wherein the indicator identifies a natural energy source associated with the second ground-based location if the second energy level exceeds the first energy level, and wherein the indicator identifies a natural energy sink associated with the second ground-based location if the second energy level does not exceed the first energy level.

2. The aerial vehicle of claim 1 , wherein the method further comprises: identifying information regarding a mission to be performed by the aerial vehicle, wherein the mission requires travel from an origin within the region to a destination within the region; selecting at least one of a path or a waypoint based at least in part on the map; and generating a route for performing the mission, wherein the route comprises the origin, the at least one of the path or the waypoint, and the destination.

3. The aerial vehicle of claim 1 , further comprising an imaging device, wherein the method further comprises: capturing an aerial photograph of the region; defining a training set comprising the aerial photograph of the region as at least one training input and the map of the region as at least one training output; training a machine learning system executed by at least one processor to associate at least one portion of an image of a region with naturally present energy in the region based at least in part on the training set; identifying an aerial photograph of another region; providing the aerial photograph of the other region to the trained machine learning system as an input; receiving an output from the trained machine learning system; and generating a map of the other region, wherein the map of the other region comprises an indicator of naturally present energy associated with at least one ground-based location of the other region.

4. A computer-implemented method comprising: calculating a first energy level of a first aerial vehicle at a first time, wherein the first energy level is calculated based at least in part on a first airspeed of the first aerial vehicle at the first time and a first altitude of the first aerial vehicle above a first ground-based location at the first time; determining a first temperature of air at the first altitude above the first ground-based location; determining that the first aerial vehicle is at a second altitude above a second ground-based location at a second time, wherein the second time follows the first time; determining a second airspeed of the first aerial vehicle at the second time; calculating a second energy level of the first aerial vehicle at the second time based at least in part on the second altitude and the second airspeed; calculating a difference between the second energy level and the first energy level; determining a second temperature of air at the second altitude above the second ground-based location; attributing the difference between the second energy level and the first energy level to naturally present energy at the second ground-based location based at least in part on a difference between the second temperature and the first temperature; and storing an indication of the naturally present energy associated with the second ground-based location at the second time in at least one data store, wherein the indication identifies a natural energy source associated with the second ground-based location if the second energy level exceeds the first energy level, and wherein the indication identifies a natural energy sink associated with the second ground-based location if the second energy level does not exceed the first energy level.

5. The computer-implemented method of claim 4 , further comprising: generating a map of a first region including at least the second ground-based location, wherein the map of the first region comprises the indication of the naturally present energy at the second ground-based location at the second time; and storing the map of the first region in the at least one data store.

6. The computer-implemented method of claim 5 , wherein generating the map of the first region comprises: determining a mass of the first aerial vehicle; determining a specific energy level associated with the second ground-based location at the second time, wherein determining the specific energy level comprises dividing the difference between the second energy level and the first energy level by the mass of the first aerial vehicle; and storing the specific energy level in association with the second ground-based location at the second time in the at least one data store.

7. The computer-implemented method of claim 5 , further comprising: identifying a first aerial photograph of the first region; defining a training set comprising the first aerial photograph of the first region as at least one training input and the map of the first region as at least one training output; training a machine learning system executed by at least one processor to associate at least one portion of an image with naturally present energy based at least in part on the training set; identifying a second aerial photograph of a second region captured at a third time; providing the second aerial photograph to the trained machine learning system as a first input; receiving a second output from the trained machine learning system; and generating a map of the second region based at least in part on the second output, wherein the map of the second region comprises an indication of naturally present energy associated with at least one ground-based location of the second region at the third time; and storing the map of the second region in the at least one data store.

8. The computer-implemented method of claim 7 , wherein the at least one machine learning system is an artificial neural network comprising an input layer of one or more neurons, an output layer of one or more neurons, and one or more intervening hidden layers, wherein each of the hidden layers comprises one or more neurons, and wherein training the machine learning system comprises: adjusting at least one synaptic weight between at least one pair of neurons based at least in part on a portion of the first aerial photograph corresponding to the second ground-based location at the second time and the difference between the second energy level and the first energy level.

9. The computer-implemented method of claim 7 , wherein the at least one computer processor resides aboard the first aerial vehicle or in at least one computer system external to the first aerial vehicle.

10. The computer-implemented method of claim 5 , further comprising: identifying a mission to be performed by one of the first aerial vehicle or a second aerial vehicle, wherein the mission requires travel from an origin within the first region to a destination within the first region; and selecting a route for performing the mission based at least in part on the map of the first region, wherein the selected route comprises at least one waypoint corresponding to the second ground-based location.

11. The computer-implemented method of claim 10 , wherein selecting the route for performing the mission comprises: identifying a plurality of routes between the origin within the first region and the destination within the first region; and determining, based at least in part on the map of the first region, an amount of energy to be consumed by the one of the first aerial vehicle or the second aerial vehicle in traveling along one of the routes, wherein the route for performing the mission is selected based at least in part on the amounts of energy to be consumed by the one of the first aerial vehicle or the second aerial vehicle in traveling along one of the routes.

12. The computer-implemented method of claim 4 , wherein the first aerial vehicle comprises: an altimeter; at least one propulsion motor; a thermometer; a position sensor; and a control system in communication with at least one of the altimeter, the at least one propulsion motor and the position sensor.

13. The computer-implemented method of claim 4 , wherein the second ground-based location corresponds to at least one of: a body of water; a water course; a roadway; a structure; or a mass of terrain, and wherein the indication identifies one of the natural energy source or the natural energy sink as associated with the at least one of the body of water, the water course, the roadway, the structure or the mass of terrain.

14. The computer-implemented method of claim 4 , wherein calculating the second energy level of the first aerial vehicle at the second time comprises: calculating a kinetic energy level of the first aerial vehicle at the second time, wherein the kinetic energy level is equal to one half of a product of a mass of the first aerial vehicle and a square of the second airspeed; calculating a potential energy level of the first aerial vehicle at the second time, wherein the potential energy level is equal to a product of the mass of the aerial vehicle, acceleration constant due to gravity, and the second altitude; determining a level of work provided by at least one propulsion motor of the first aerial vehicle at the second time; and subtracting the level of work from a sum of the kinetic energy level and the potential energy level, wherein the second energy level is the sum of the kinetic energy level and the potential energy level with the level of work subtracted therefrom.

15. The computer-implemented method of claim 4 , wherein the second temperature is greater than the first temperature.

16. A method comprising: identifying a plurality of images, wherein each of the plurality of images depicts one of a plurality of regions, and wherein each of the plurality of images was captured using at least one imaging device carried aboard one of an aerial vehicle or an orbiting satellite; identifying a plurality of maps, wherein each of the plurality of maps corresponds to one of the plurality of regions, and wherein each of the plurality of maps depicts at least one area within the one of the plurality of regions corresponding to a naturally present energy source or at least one area within the one of the plurality of regions corresponding to a naturally present energy sink within the one of the regions; defining a training set comprising at least a subset of the plurality of images and at least a subset of the plurality of maps, wherein each of the plurality of images of the subset depicts a region corresponding to one of the plurality of maps of the subset; training at least one machine learning system to recognize naturally present energy within a region based at least in part on imaging data depicting at least a portion of the region using at least the training set; identifying a first image depicting at least a portion of a first region, wherein the first image was captured using an imaging device carried aboard one of an aerial vehicle or an orbiting satellite; providing the first image to the at least one trained machine learning system as a first input; receiving a first output from the at least one trained machine learning system in response to the first input; and generating a first map based at least in part on the first output, wherein the first map depicts at least one of a first area within the first region corresponding to a naturally present energy source or a second area within the first region corresponding to a naturally present energy sink.

17. The method of claim 16 , wherein the at least one machine learning system is an artificial neural network comprising an input layer of one or more neurons, an output layer of one or more neurons, and one or more intervening hidden layers, wherein each of the hidden layers comprises one or more neurons, and wherein training the at least one machine learning system comprises: adjusting, by at least one computer processor at least one synaptic weight between at least one pair of neurons based at least in part on at least one of the subset of the plurality of images and at least one of the subset of the plurality of maps.

18. The method of claim 16 , further comprising: detecting, by each of a plurality of aerial vehicles traveling within a region, at least one change in altitude of one of the aerial vehicles; determining, by each of the plurality of aerial vehicles, a location within the region associated with the at least one change in altitude; and generating one of the plurality of maps based at least in part on the at least one change in altitude of each of the aerial vehicles and the location within the region of the at least one changes.

19. The method of claim 16 , further comprising: identifying a plurality of routes between an origin within the first region and a destination within the first region; determining, based at least in part on the first map, an amount of energy to be consumed by a first aerial vehicle in traveling along each of the routes; and selecting a route for traveling from the origin to the destination based at least in part on the first map, wherein the route for performing the mission is selected based at least in part on the amounts of energy to be consumed by the first aerial vehicle in traveling along each of the routes.